Join us for
RADAR: AI Edition
Learn R Programming
textir (version 1.4)

plot.mnlm: Multinomial logistic regression Plots

Description

Plot function for mnlm objects, the output of multinomial logistic regression.

Usage

## S3 method for class 'mnlm':
plot(x, covar=NULL, v=NULL, cat=NULL, delta=0.05, xlab=NULL, ylab=NULL,...)

Arguments

x
An output object from the mnlm function.
covar
The covariate direction to plot. Defaults to 1.
v
Optional argument for the fitted reduction to be plotted against (if, e.g., you wish to plot against unnormalized response).
cat
An optional category in 1:(ncol(fit$X)). If specified, plot the conditional bound and likelihood functions for that category around the converged solution.
delta
Optional argument for the delta used by the bounding function (and plot xlim) when cat is specified. Defaults to 0.05.
xlab
The x-axis label; will be automatically set if NULL.
ylab
The y-axis label; will be automatically set if NULL.
...
Additional plot arguments

Value

  • A fabulous plot.

Details

Can be used to reproduce all of the plots (except wordles; see http://wordle.net) from Taddy (2011). If cat=NULL, just plots the fitted reductions freq(counts)%*%coef[,covar+1] for inverse regression based on this mnlm fit. If cat is specified, plots the objective near solution for that multinomial category coefficient.

References

Taddy (2011), Inverse Regression for Analysis of Sentiment in Text. http://arxiv.org/abs/1012.2098

See Also

mnlm, congress109, we8there